| { | |
| "_name_or_path": "./", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_dropout": 0.1, | |
| "attn_pdrop": 0.1, | |
| "beta1": 0.9, | |
| "beta2": 0.98, | |
| "bos_token_id": 8, | |
| "data_path": "", | |
| "embd_pdrop": 0.1, | |
| "embed_dropout": 0.1, | |
| "eos_token_id": 9, | |
| "epsilon": 1e-09, | |
| "eval_batch_size": 128, | |
| "eval_steps": 10, | |
| "gradient_checkpointing": false, | |
| "initializer_range": 0.02, | |
| "iterations": 1000, | |
| "layer_norm_epsilon": 1e-05, | |
| "line_count": 1, | |
| "lr": 0.00025, | |
| "max_steps": 3600000, | |
| "model": "GPT2", | |
| "model_type": "gpt2", | |
| "n_ctx": 256, | |
| "n_embd": 1024, | |
| "n_head": 16, | |
| "n_inner": null, | |
| "n_layer": 24, | |
| "n_positions": 256, | |
| "n_vocab": 25000, | |
| "opt_name": "adam", | |
| "precision": "float32", | |
| "predict_batch_size": 8, | |
| "reorder_and_upcast_attn": false, | |
| "res_dropout": 0.1, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "scale_by_depth": true, | |
| "scale_by_in": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 512 | |
| } | |
| }, | |
| "tokenizer_class": "AlbertTokenizer", | |
| "torch_dtype": "float32", | |
| "train_batch_size": 320, | |
| "train_steps": 10000, | |
| "transformers_version": "4.12.3", | |
| "use_cache": true, | |
| "vocab_size": 25000, | |
| "warmup_steps": 2000, | |
| "weight_decay": 0.01 | |
| } | |